Neural Hopfield-ensemble for multi-class head pose detection

被引:0
|
作者
Meins, Nils [1 ]
Magg, Sven [1 ]
Wermter, Stefan [1 ]
机构
[1] Univ Hamburg, Dept Informat, Knowledge Technol Grp, D-22527 Hamburg, Germany
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multi-class object detection is perhaps the most important task for many computer vision systems and mobile robots. In this work we will show that Hopfield Neural Network (HNN) ensembles can successfully detect and classify objects from several classes by taking advantage of head-pose estimation. The single HNNs are using pixel sums of Haarlike features as input, resulting in HNNs with a small number of neurons. An advantage of using these in ensembles is their compact form. Although it was shown that such HNNs can only memorise few patterns, by utilising a naive-Bayes mechanism we were able to exploit the multi-class ability of single HNNs within an ensemble. In this work we report successful head pose classification, which presents a 4-class problem (3 poses + negatives). Results show that successful classification can be achieved with small training sets and ensembles, making this approach an interesting choice for online learning and robotics.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] HEAD POSE ESTIMATION THROUGH MULTI-CLASS FACE SEGMENTATION
    Khan, Khalil
    Mauro, Massimo
    Migliorati, Pierangelo
    Leonardi, Riccardo
    2017 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2017, : 175 - 180
  • [2] Ensemble-learning based neural networks for novelty detection in multi-class systems
    Chan, Felix T. S.
    Wang, Z. X.
    Patnaik, S.
    Tiwari, M. K.
    Wang, X. P.
    Ruan, J. H.
    APPLIED SOFT COMPUTING, 2020, 93
  • [3] Multi-class WHMBoost: An ensemble algorithm for multi-class imbalanced data
    Zhao, Jiakun
    Jin, Ju
    Zhang, Yibo
    Zhang, Ruifeng
    Chen, Si
    INTELLIGENT DATA ANALYSIS, 2022, 26 (03) : 599 - 614
  • [4] Head Pose Classification by Multi-Class AdaBoost with Fusion of RGB and Depth Images
    Yun, Yixiao
    Changrampadi, Mohamed H.
    Gu, Irene Y. H.
    2014 INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND INTEGRATED NETWORKS (SPIN), 2014, : 174 - +
  • [5] EBDM: Ensemble binary detection models for multi-class wireless intrusion detection based on deep neural network
    Tseng, Chinyang Henry
    Chang, Ya-Ting
    COMPUTERS & SECURITY, 2023, 133
  • [6] Multi-Scale Convolutional Neural Network Ensemble for Multi-Class Arrhythmia Classification
    Prabhakararao, Eedara
    Dandapat, Samarendra
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2022, 26 (08) : 3802 - 3812
  • [7] Ensemble Learning for UAV Detection: Developing a Multi-Class Multimodal Dataset
    Mccoy, James
    Rawal, Atul
    Rawat, Danda B.
    2023 IEEE 24TH INTERNATIONAL CONFERENCE ON INFORMATION REUSE AND INTEGRATION FOR DATA SCIENCE, IRI, 2023, : 101 - 106
  • [8] Convolutional Neural Networks for Multi-class Intrusion Detection System
    Potluri, Sasanka
    Ahmed, Shamim
    Diedrich, Christian
    MINING INTELLIGENCE AND KNOWLEDGE EXPLORATION, MIKE 2018, 2018, 11308 : 225 - 238
  • [9] Multi-class SAR feature space trajectory (FST) neural network class and pose estimation results
    Shenoy, R
    Casasent, D
    ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY IV, 1997, 3070 : 121 - 124
  • [10] Class-overlap detection based on heterogeneous clustering ensemble for multi-class imbalance problem
    Dai, Qi
    Wang, Long-hui
    Xu, Kai-long
    Du, Tony
    Chen, Li -fang
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 255